GPT-5.6 Terra (Non-reasoning): benchmark results
GPT-5.6 Terra evaluated with reasoning disabled. Provider: OpenAI. Released 2026-07-09. Access: API.
Unified ELO 1622 ± 1, rank #347 of 1761 rated models, from 24 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Natural Intelligence | 52.63 | NatInt Score | 90.9 |
| UGI - Writing | 48.2 | Writing Score | 87.5 |
| UGI Leaderboard | 47.66 | UGI Score | 85.4 |
| AA Omniscience - Software Engineering (SWE) | 61.2 | Accuracy (%) | 84.2 |
| AA Omniscience - Health | 36.4 | Accuracy (%) | 82.8 |
| AA-Omniscience Accuracy | 36.82 | Accuracy (%) | 79.6 |
| AA Omniscience - Law | 27 | Accuracy (%) | 78.3 |
| AA Omniscience - Business | 27 | Accuracy (%) | 77.2 |
| AA Omniscience - Humanities & Social Sciences | 31.5 | Accuracy (%) | 77 |
| AA Omniscience - Science, Engineering & Mathematics | 37.8 | Accuracy (%) | 75.3 |
| Artificial Analysis Intelligence Index | 26.3 | Intelligence Index | 74.8 |
| AA CritPt | 2 | Accuracy (%) | 70.6 |
Interactive version: theaggregate.ai/model?slug=gpt-5-6-terra-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.